Instructions to use EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL

Use Docker

docker model run hf.co/EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL

LM Studio
Jan

vLLM

How to use EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Install mistral-common:
pip install --upgrade mistral-common
# Start the vLLM server:
vllm serve "EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF" --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL

Ollama
How to use EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF with Ollama:
```
ollama run hf.co/EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL
```
Unsloth Desktop
Docker Model Runner
How to use EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF with Docker Model Runner:
```
docker model run hf.co/EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL
```

Lemonade

How to use EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF:Q4_K_XL

Run and chat with the model

lemonade run user.Pixtral-Large-Instruct-2411-GGUF-Q4_K_XL

List all available models

lemonade list

Atomic Chat

Model - Pixtral-Large-Instruct-2411 (GGUF + Quantized)

[The first Pixtral-Large-Instruct-2411 124B to be GGUF converted and Quantized!]

NEW UPDATES! (As of: September 20th, 2026) (Read below!)

PLEASE NOTE, FILES ARE STILL UPLOADING!!!
This is a rather large model, please check back soon if you do not see any quant files available! The quantized files are currently being uploaded right now, as fast as my network connection will allow for it!

Description:
EnlistedGhost's GGUF/Quantized Repository of - MistralAI Pixtral-Large-2411 124B This release includes GGUF + Quantized model files and three mmproj multi-model projector Quants (mmproj) files for the Vision Projector, offering full capabilities in Yollama, Ollama or Llama.cpp.

No modifications, edits, or configurations are required to use this model with Yollama, Ollama, and Llama.cpp it works natively! Both Vision and Text work! (^.^)

Personal Notes:
The quality of interaction with this model from MistralAI is absolutely phenomenal quality! This model originally seems to have slipped through the cracks and although it was a little "tricky" to get this model to convert- it was successfully converted with official MistralAI weights using Llama.cpp b8940
(Works with any recent Llama.cpp version) Thank you for taking the time to read this!

Source Model:
The linked MistralAI release is the source model. However, I did upload a configuration file edit along with properly adjusted safetensors files (Big thanks to @Rocketknight1 !) that were then used to be able to achieve this conversion. These files are available by going to this Safetensors model release: [EnlistedGhost/Pixtral-Large-Instruct-2411-hf]

Happy Inferencing!
-- Jon Z (EnlistedGhost)

Model Updates (As of: September 20th, 2026)

Uploading Quantized files at this time! If you don't see a quant that you are looking for, be sure to check back soon!

How to run this Model

You can run this model by using Yollama, Ollama, or Llama.cpp Model Runners (Software)
GGUF Quantized Files (Note: the "status" field will be replaced with quality assessment)

Quant Type	File Size	Status
Q2_K	44.6 GB	Available!
Q2_K_L	58.6 GB	Available!
Q3_K_L	66.5 GB	Available!
Q4_K_XL	77.4 GB	Available!
Q5_K_XL	96.1 GB	Available!
Q6_K_L	106.7 GB	Available!
Q8_0	N/A	Queued
F16	245 GB	Queued

mmproj (Vision Projector) Files (Note: the "status" field will be replaced with quality assessment)

Quant Type	File Size	Status
Q8_0	1.62 GB	Available!
F16	3.04 GB	Available!
F32	6.09 GB	Available!

Intended Use

Same as original:

[MistralAI]

Out-of-Scope Use

Same as original:

[MistralAI]

Bias, Risks, and Limitations

Same as original:

[MistralAI]

Training Details

Training sets and data are from:

[mistralAI]
(This is a direct off-shoot/decendant of the above mentioned model)

Evaluation

This model has NOT been evaluated in any form, scope or type of method.
!!! USE AT YOUR OWN RISK !!!
!!! NO WARRANTY IS PROVIDED OF ANY KIND !!!

Detailed Release Information

Originally Developed by: [mistralai]
MMPROJ (Vision) Quantized by: [EnlistedGhost]
GGUF Converted and Quantized by: [EnlistedGhost]
Model type & format: [Quantized/GGUF]
License type: [Mistral AI Research License]

Attributions (Credits)

A big thank-you is extended to the below credited sources!
These contributions are what made this release possible!

Important Notice: This is NOT a copy/paste release,
I have created unique Quantized files that were then altered further
to function and work with improved quality.
This resulted in the first publicly available
Pixtral-Large-2411 124B model in GGUF format and Quantized

Model Card Authors and Contact

[EnlistedGhost]

Downloads last month: 779

GGUF

Model size

123B params

Architecture

mistral3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

Model tree for EnlistedGhost/Pixtral-Large-Instruct-2411-GGUF

Base model

mistralai/Pixtral-Large-Instruct-2411

Quantized

(11)

this model